Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active. https://librechat.ai/
Find a file
Marco Beretta eb5d74dbd5 🧑‍🎨 feat: Give the Default Avatar and Avatar Placeholder Theme Roles (#16545)
* feat: Give the Default Avatar and Avatar Placeholder Theme Roles

The default user avatar filled with a literal rgb(121, 137, 255) in Avatar, MessageIcon and the endpoint Icon, and agent and assistant avatars sat on surface-secondary in light and a dark: surface-tertiary override, so no theme could repaint either.

avatar-fill and avatar-text paint the default avatar and its glyph, and avatar-placeholder paints the backdrop behind an agent or assistant image. Every bundled theme reproduces today's pixels. A theme that sets only its surfaces keeps the placeholder on the surface its mode used before the role existed, both when resolved and through the legacy applyTheme path. ClickHouse takes Click UI's avatar fill and text and its muted background.

* test: Pin the Default Avatar Fill With and Without the ClickHouse Theme

The sidebar account avatar falls back to the default avatar when its image fails; with no theme it keeps rgb(121, 137, 255) in both modes and the placeholder keeps the surface its mode used, and under ClickHouse both take the Click UI values.

* fix: Ink Every Default Avatar Glyph With the Avatar Text Role

The sidebar Avatar, the only default avatar the chat renders, still inked its glyph in text-primary, so a theme's avatar-text never reached it and ClickHouse drew a dark glyph where Click UI draws white. Avatar now reads avatar-text, which defaults to each bundled theme's primary text and follows rgb-text-primary in a theme that does not set it, through resolveTheme and the legacy applyTheme path, so every rendered default avatar keeps its pixels.

* fix: Read the Active Mode Off the Root When applyTheme Is Not Told It

applyTheme is exported, and a caller that applies a legacy palette in dark mode without the new mode argument derived the avatar placeholder from the light surface. It now falls back to the root's dark class.

* fix: Keep CSS-Themed Avatars on Their Legacy Source Variables

The avatar text and placeholder defaults were literal triplets, so a consumer theming through --text-primary and the surface variables left avatars on the stock colors. They now alias text-primary, the secondary surface and, in dark, the tertiary surface, resolving to the same pixels by default. applyTheme's mode fallback also reads a dark ancestor, not only the root itself.

* fix: Let the Stylesheet Alias Carry the Document Root Avatar Backdrop

applyTheme wrote the legacy placeholder inline for the mode active when it ran, which then overrode the per-mode stylesheet alias after a dark toggle without a reapply. On the document root the alias already follows the theme's surfaces and the mode, so the placeholder is now derived only for a scoped root, which that alias cannot see.

* fix: Keep a Scoped Legacy Avatar Backdrop Following the Mode

applyTheme wrote a scoped root's avatar placeholder inline for the mode active when it ran, so after a later dark toggle the backdrop stayed on the light surface, where canary's dark:bg-surface-tertiary switched. applyTheme now marks a scoped root with data-theme-scope and the stylesheet points its backdrop at that root's own secondary surface, or its tertiary one under a .dark ancestor, as the document root's alias does. The mode argument is no longer needed and is removed.

(cherry picked from commit 3ac6a0af37)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/16545
2026-10-01 03:46:19 +00:00
.claude/skills
.devcontainer
.github 🫸 fix: Gate MCP App Views and Actions on User Intent (#16297) 2026-10-01 03:46:17 +00:00
.husky 🎨 chore: Enforce Design-System Rules With @shadcn/lint (#15981) 2026-10-01 03:46:16 +00:00
.vscode
api 🎒 feat: Carry Project Context Across Conversations (#15684) 2026-10-01 03:46:19 +00:00
client 🧑‍🎨 feat: Give the Default Avatar and Avatar Placeholder Theme Roles (#16545) 2026-10-01 03:46:19 +00:00
config 🧯 fix: Outlast Failed Auth Cache Eviction on Credential Changes (#16435) 2026-10-01 03:46:18 +00:00
docs 🫗 fix: Bound MCP App Responses and In-Flight Work (#16300) 2026-10-01 03:46:17 +00:00
e2e 🧑‍🎨 feat: Give the Default Avatar and Avatar Placeholder Theme Roles (#16545) 2026-10-01 03:46:19 +00:00
helm 🎁 chore: Bump Packages and Helm After Security Fixes (#16582) 2026-09-30 22:35:22 -04:00
otel/langfuse-fanout 📤 fix(langfuse): support documented media upload types (#16079) 2026-09-19 09:03:32 -04:00
packages 🧑‍🎨 feat: Give the Default Avatar and Avatar Placeholder Theme Roles (#16545) 2026-10-01 03:46:19 +00:00
redis-config 🚚 chore: Point Repository and Image References at LibreChat-AI (#16005) 2026-09-23 23:08:36 -04:00
scripts 🔤 fix: Ship the Theme Font Faces With the Package (#16485) 2026-10-01 03:46:18 +00:00
search
skill
src/tests 💬 refactor: ChatForm UI redesign with unified palette (#14473) 2026-10-01 03:46:18 +00:00
utils 🚚 chore: Point Repository and Image References at LibreChat-AI (#16005) 2026-09-23 23:08:36 -04:00
.codex
.dockerignore
.env.example ⚙️ feat: Make the Per-User Passkey Cap Configurable (#16259) 2026-10-01 03:46:17 +00:00
.gitattributes
.gitignore 🔔 feat: Unseen Reply Indicators, Reply Notifications, and Mark as Unread (#15025) 2026-10-01 03:46:16 +00:00
.npmrc ⛔ fix: Bind Tool Approvals to Generation Scope (#15724) 2026-09-08 08:02:48 -04:00
.nvmrc
.prettierignore 🔌 feat: OpenAPI spec and docs for the public Agents API (#15928) 2026-09-16 13:50:05 -04:00
.prettierrc
AGENTS.md 🎨 chore: Enforce Design-System Rules With @shadcn/lint (#15981) 2026-10-01 03:46:16 +00:00
bun.lock 🧵 fix: Restore Classes tailwind-merge Was Silently Dropping (#15995) 2026-10-01 03:46:16 +00:00
CONTEXT.md 🪂 feat: Opt-In Text Fallback for Files No Tool Can Read (#15940) 2026-09-14 21:02:54 -04:00
deploy-compose.langfuse-fanout.yml
deploy-compose.yml 🚚 chore: Point Repository and Image References at LibreChat-AI (#16005) 2026-09-23 23:08:36 -04:00
docker-compose.langfuse-fanout.yml
docker-compose.override.yml.example 🚚 chore: Point Repository and Image References at LibreChat-AI (#16005) 2026-09-23 23:08:36 -04:00
docker-compose.yml 🚚 chore: Point Repository and Image References at LibreChat-AI (#16005) 2026-09-23 23:08:36 -04:00
Dockerfile 🧩 feat: MCP Apps support (#13831) 2026-10-01 03:46:16 +00:00
Dockerfile.multi 🧩 feat: MCP Apps support (#13831) 2026-10-01 03:46:16 +00:00
eslint-suppressions.json 🧑‍🎨 feat: Give the Default Avatar and Avatar Placeholder Theme Roles (#16545) 2026-10-01 03:46:19 +00:00
eslint.config.mjs 💬 refactor: ChatForm UI redesign with unified palette (#14473) 2026-10-01 03:46:18 +00:00
librechat.example.yaml 🎒 feat: Carry Project Context Across Conversations (#15684) 2026-10-01 03:46:19 +00:00
LICENSE
package-lock.json 🧩 feat: MCP Apps support (#13831) 2026-10-01 03:46:16 +00:00
package.json 🎨 feat: Check Color Tokens and Class Existence (#16041) 2026-10-01 03:46:16 +00:00
rag.yml 🚚 chore: Point Repository and Image References at LibreChat-AI (#16005) 2026-09-23 23:08:36 -04:00
README.md 🚀 v0.8.8 (#15735) 2026-09-29 23:55:37 -04:00
README.zh.md 🚚 chore: Point Repository and Image References at LibreChat-AI (#16005) 2026-09-23 23:08:36 -04:00
tool-intent-spec.md
turbo.json
UPGRADING.md 🚐 perf: Enable Redis Stream Coalescing by Default (#16093) 2026-09-19 13:04:43 -04:00

LibreChat

English · 中文

Deploy on Railway Deploy on Zeabur Deploy on Sealos

Translation Progress

🚀 What's New in v0.8.8

  • Agent Management API (beta): Create, discover, update, and delete Agents; manage Agent files and Skills; and authenticate machine clients through deployment-bound OIDC identities while preserving existing role and Agent access controls. Public OpenAPI and Swagger UI cover inference, events, Agent management, and Skill management.
  • Attached workspaces (highly experimental): Select or save a per-Agent default workspace for each managed or personal code worker, then let Agents inspect trees, read and search files, author changes, and run Bash with bounded timeouts. Personal workers support bounded self-service enrollment, readiness status, and per-Agent Git identity.
  • Background tool controls: Optionally cancel ordinary background tools, including attached Bash, while keeping detached Subagent execution independent.
  • Code approval controls: Choose Ask, Allow, or Deny for file writes and command execution where administrators permit it, including a Full access mode for trusted attached environments. File Search and Run Code also honor role grants.
  • Manual context compaction: Start a summarize-only turn before the context window fills while preserving recent conversation content according to the deployment's summarization policy.
  • Context Usage: Inspect dialogue, retained tool traffic, Agent instructions, cache, cost, and runway pressure without double-counting category subsets.
  • Unified attachments: Upload once and let LibreChat route content to the model or extracted text, then provision File Search and Code tools only when needed.
  • Models: Added GPT-6 Astra and GPT-6.1 Sol, with Responses API routing and tool-call support.
  • Agent and chat UI: Unified tool activity, reasoning, search, and Agent workflows; added one draggable Pinned section for chats and favorites, morphing state icons, high-contrast themes, rich-text message copying, clearer sidebar titles, and refined live phase layouts.
  • Observability: Inspect ordered model conversations, tool rounds, and costs in the Trace Viewer; export correlated application logs through OpenTelemetry, configure allowlisted Langfuse trace identity and metadata, tag browser diagnostics with client build IDs, and scope Insights to authorized Agents.
  • Reliability and security: Strengthened Agent continuation and checkpoint recovery, Redis liveness detection, DocumentDB coordination, OpenID and MCP OAuth sessions, shared-link throttling, tenant isolation, attachment bounds, and upload error handling.

Read the full v0.8.8 changelog.

✨ Features

  • 🖥️ UI & Experience inspired by ChatGPT with enhanced design and features

  • 🤖 AI Model Selection:

    • Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, OpenAI Responses API (incl. Azure)
    • Custom Endpoints: Use any OpenAI-compatible API with LibreChat, no proxy required
    • Compatible with Local & Remote AI Providers:
      • Ollama, AMD Lemonade, groq, Cohere, Mistral AI, Apple MLX, koboldcpp, together.ai,
      • OpenRouter, Helicone, Perplexity, ShuttleAI, Deepseek, Qwen, and more
  • 🔧 Code Interpreter API:

    • Secure, Sandboxed Execution in Python, Node.js (JS/TS), Go, C/C++, Java, PHP, Rust, and Fortran
    • Seamless File Handling: Upload, process, and download files directly
    • No Privacy Concerns: Fully isolated and secure execution
    • Open-Source & Self-Hostable: powered by ClickHouse/code-interpreter
  • 🔦 Agents & Tools Integration:

    • LibreChat Agents:
      • No-Code Custom Assistants: Build specialized, AI-driven helpers
      • Agent Marketplace: Discover and deploy community-built agents
      • Collaborative Sharing: Share agents with specific users and groups
      • Flexible & Extensible: Use MCP Servers, tools, file search, code execution, and more
      • Skills: Create reusable SKILL.md instruction bundles for manual, automatic, or always-on agent workflows
      • Agent Plugins: Experimentally bundle deployment Skills and MCP servers into startup-loaded packages
      • Subagents: Delegate focused work to isolated child agent runs with their own context windows
      • Agent Management API: Automate Agent, file, and Skill management with deployment-bound OIDC clients
      • Attached Code Workspaces: Let Agents inspect, search, edit, and run commands in managed or personal workspaces (highly experimental)
      • Compatible with Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, Google, Vertex AI, Responses API, and more
      • Model Context Protocol (MCP) Support for Tools
  • 🔍 Web Search:

    • Search the internet and retrieve relevant information to enhance your AI context
    • Combines search providers, content scrapers, and result rerankers for optimal results
    • Customizable Jina Reranking: Configure custom Jina API URLs for reranking services
    • Learn More →
  • 🪄 Generative UI with Code Artifacts:

    • Code Artifacts create React, HTML, and Mermaid content directly in chat
    • Open previews fullscreen and export Mermaid diagrams as SVG or PNG
  • 🎨 Image Generation & Editing

  • 💾 Presets & Context Management:

    • Create, Save, & Share Custom Presets
    • Switch between AI Endpoints and Presets mid-chat
    • Edit, Resubmit, and Continue Messages with Conversation branching
    • Create and share prompts with specific users and groups
    • Fork Messages & Conversations for Advanced Context control
    • Compact long conversations on demand while preserving recent context
  • 💬 Multimodal & File Interactions:

    • Upload and analyze images with Claude 3, GPT-4.5, GPT-4o, o1, Llama-Vision, and Gemini 📸
    • Chat with Files using Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, & Google 🗃️
    • Copy messages as formatted rich text for documents, email, and collaboration apps
  • 🌎 Multilingual UI:

    • English, 中文 (简体), 中文 (繁體), العربية, Deutsch, Español, Français, Italiano
    • Polski, Português (PT), Português (BR), Русский, 日本語, Svenska, 한국어, Tiếng Việt
    • Türkçe, Nederlands, עברית, Català, Čeština, Dansk, Eesti, فارسی
    • Suomi, Magyar, Հայերեն, Bahasa Indonesia, ქართული, Latviešu, ไทย, ئۇيغۇرچە
  • 🧠 Reasoning UI:

    • Dynamic Reasoning UI for Chain-of-Thought/Reasoning AI models like DeepSeek-R1
  • 🎨 Customizable Interface:

    • Customizable Dropdown & Interface that adapts to both power users and newcomers
    • Light, dark, system, and high-contrast appearance modes
  • 📈 Observability:

    • Export traces and logs with OpenTelemetry and connect Langfuse for Agent and model insights
  • 🌊 Resumable Streams:

    • Never lose a response: AI responses automatically reconnect and resume if your connection drops
    • Multi-Tab & Multi-Device Sync: Open the same chat in multiple tabs or pick up on another device
    • Production-Ready: Works from single-server setups to horizontally scaled deployments with Redis
  • 🗣️ Speech & Audio:

    • Chat hands-free with Speech-to-Text and Text-to-Speech
    • Automatically send and play Audio
    • Supports OpenAI, Azure OpenAI, and Elevenlabs
  • 📥 Import & Export Conversations:

    • Import Conversations from LibreChat, ChatGPT, Chatbot UI
    • Export conversations as screenshots, markdown, text, json
  • 🔍 Search & Discovery:

    • Search all messages/conversations
  • 👥 Multi-User & Secure Access:

    • Multi-User, Secure Authentication with OAuth2, LDAP, & Email Login Support
    • Built-in Moderation, and Token spend tools
  • 🎛️ Admin Panel:

    • Browser-based UI to manage users, groups, roles, and configuration overrides
    • Edit settings and per-role/group permissions live, without redeploying
    • Bundled with the Docker Compose stacks for one-command setup
  • ⚙️ Configuration & Deployment:

    • Configure Proxy, Reverse Proxy, Docker, & many Deployment options
    • Use S3 with CloudFront for stable media links, edge delivery, signed cookies, and secured downloads
    • Use completely local or deploy on the cloud
  • 📖 Open-Source & Community:

    • Completely Open-Source & Built in Public
    • Community-driven development, support, and feedback

For a thorough review of our features, see our docs here 📚

🪶 All-In-One AI Conversations with LibreChat

LibreChat is a self-hosted AI chat platform that unifies all major AI providers in a single, privacy-focused interface.

Beyond chat, LibreChat provides AI Agents, Model Context Protocol (MCP) support, Artifacts, Code Interpreter, custom actions, conversation search, and enterprise-ready multi-user authentication.

Open source, actively developed, and built for anyone who values control over their AI infrastructure.


🌐 Resources

GitHub Repo:

Other:


📝 Changelog

Keep up with the latest updates by visiting the releases page and notes:

⚠️ Please consult the changelog for breaking changes before updating.


⭐ Star History

Star History Chart

LibreChat-AI%2FLibreChat | Trendshift ROSS Index - Fastest Growing Open-Source Startups in Q1 2024 | Runa Capital


✨ Contributions

Contributions, suggestions, bug reports and fixes are welcome!

For new features, components, or extensions, please open an issue and discuss before sending a PR.

If you'd like to help translate LibreChat into your language, we'd love your contribution! Improving our translations not only makes LibreChat more accessible to users around the world but also enhances the overall user experience. Please check out our Translation Guide.


💖 This project exists in its current state thanks to all the people who contribute


🎉 Special Thanks

We thank Locize for their translation management tools that support multiple languages in LibreChat.

Locize Logo